Penguin Data EDA

HW: Label the entire notebook with comments on what operation is each code chunk doing and what is the outcome

library(tidyverse)
library(plotly)
Penguins<-read.csv("penguins_size.csv")

We see that the data has 344 rows and 7 columns

Penguins

dim(Penguins)

[1] 344   7

Looking at summary stats

summary(Penguins)

   species             island          culmen_length_mm culmen_depth_mm flipper_length_mm
 Length:344         Length:344         Min.   :32.10    Min.   :13.10   Min.   :172.0    
 Class :character   Class :character   1st Qu.:39.23    1st Qu.:15.60   1st Qu.:190.0    
 Mode  :character   Mode  :character   Median :44.45    Median :17.30   Median :197.0    
                                       Mean   :43.92    Mean   :17.15   Mean   :200.9    
                                       3rd Qu.:48.50    3rd Qu.:18.70   3rd Qu.:213.0    
                                       Max.   :59.60    Max.   :21.50   Max.   :231.0    
                                       NA's   :2        NA's   :2       NA's   :2        
  body_mass_g       sex           
 Min.   :2700   Length:344        
 1st Qu.:3550   Class :character  
 Median :4050   Mode  :character  
 Mean   :4202                     
 3rd Qu.:4750                     
 Max.   :6300                     
 NA's   :2                        

We notice that Species and island are read in as characters. We will convert them to factor.

Penguins$species<-as.factor(Penguins$species)
Penguins$island<-as.factor(Penguins$island)
Penguins$sex<-as.factor(Penguins$sex)

Looking at summary again

summary(Penguins)

      species          island    culmen_length_mm culmen_depth_mm flipper_length_mm
 Adelie   :152   Biscoe   :168   Min.   :32.10    Min.   :13.10   Min.   :172.0    
 Chinstrap: 68   Dream    :124   1st Qu.:39.23    1st Qu.:15.60   1st Qu.:190.0    
 Gentoo   :124   Torgersen: 52   Median :44.45    Median :17.30   Median :197.0    
                                 Mean   :43.92    Mean   :17.15   Mean   :200.9    
                                 3rd Qu.:48.50    3rd Qu.:18.70   3rd Qu.:213.0    
                                 Max.   :59.60    Max.   :21.50   Max.   :231.0    
                                 NA's   :2        NA's   :2       NA's   :2        
  body_mass_g       sex     
 Min.   :2700   .     :  1  
 1st Qu.:3550   FEMALE:165  
 Median :4050   MALE  :168  
 Mean   :4202   NA's  : 10  
 3rd Qu.:4750               
 Max.   :6300               
 NA's   :2                  

We will remove the null values and also any erroneous values for sex

Clean_DF<-na.omit(Penguins)
Clean_DF<-Clean_DF%>%
  filter(sex == 'FEMALE' | sex == 'MALE')

This leaves us with the below summary stats:

summary(Clean_DF)

      species          island    culmen_length_mm culmen_depth_mm flipper_length_mm
 Adelie   :146   Biscoe   :163   Min.   :32.10    Min.   :13.10   Min.   :172      
 Chinstrap: 68   Dream    :123   1st Qu.:39.50    1st Qu.:15.60   1st Qu.:190      
 Gentoo   :119   Torgersen: 47   Median :44.50    Median :17.30   Median :197      
                                 Mean   :43.99    Mean   :17.16   Mean   :201      
                                 3rd Qu.:48.60    3rd Qu.:18.70   3rd Qu.:213      
                                 Max.   :59.60    Max.   :21.50   Max.   :231      
  body_mass_g       sex           
 Min.   :2700   Length:333        
 1st Qu.:3550   Class :character  
 Median :4050   Mode  :character  
 Mean   :4207                     
 3rd Qu.:4775                     
 Max.   :6300                     

Clean_DF$sex<-as.factor(Clean_DF$sex)

summary(Clean_DF)

      species          island    culmen_length_mm culmen_depth_mm flipper_length_mm
 Adelie   :146   Biscoe   :163   Min.   :32.10    Min.   :13.10   Min.   :172      
 Chinstrap: 68   Dream    :123   1st Qu.:39.50    1st Qu.:15.60   1st Qu.:190      
 Gentoo   :119   Torgersen: 47   Median :44.50    Median :17.30   Median :197      
                                 Mean   :43.99    Mean   :17.16   Mean   :201      
                                 3rd Qu.:48.60    3rd Qu.:18.70   3rd Qu.:213      
                                 Max.   :59.60    Max.   :21.50   Max.   :231      
  body_mass_g       sex     
 Min.   :2700   FEMALE:165  
 1st Qu.:3550   MALE  :168  
 Median :4050               
 Mean   :4207               
 3rd Qu.:4775               
 Max.   :6300               

boxplot(Clean_DF[3:5])

boxplot(Clean_DF$body_mass_g)

p<-ggplot(Clean_DF, aes(sex, body_mass_g, fill=sex))+
  geom_boxplot()

ggplotly(p)

p<-ggplot(Clean_DF, aes(sex, culmen_length_mm, fill=sex))+
  geom_boxplot()

ggplotly(p)

p<-ggplot(Clean_DF, aes(sex, culmen_depth_mm, fill=sex))+
  geom_boxplot()

ggplotly(p)

p<-ggplot(Clean_DF, aes(sex, flipper_length_mm, fill=sex))+
  geom_boxplot()

ggplotly(p)

Looking at body measures by Species

p<-ggplot(Clean_DF, aes(species, body_mass_g, fill=species))+
  geom_boxplot()

ggplotly(p)

p<-ggplot(Clean_DF, aes(species, culmen_length_mm, fill=species))+
  geom_boxplot()

ggplotly(p)

p<-ggplot(Clean_DF, aes(species, culmen_depth_mm, fill=species))+
  geom_boxplot()

ggplotly(p)

p<-ggplot(Clean_DF, aes(species, flipper_length_mm, fill=species))+
  geom_boxplot()

ggplotly(p)

p<-ggplot(data = Clean_DF) + 
  geom_bar(mapping = aes(x = species, fill=species))

ggplotly(p)

p<-ggplot(data = Clean_DF) + 
  geom_bar(mapping = aes(x = island, fill=species))

ggplotly(p)

p<-ggplot(data = Clean_DF) + 
  geom_point(mapping = aes(x = culmen_length_mm, y = culmen_depth_mm,color = species, shape=island))

ggplotly(p)

p<-ggplot(data = Clean_DF) + 
  geom_point(mapping = aes(x = culmen_length_mm, y = flipper_length_mm,color = species, shape=island))

ggplotly(p)

p<-ggplot(data = Clean_DF) + 
  geom_point(mapping = aes(x = culmen_length_mm, y = body_mass_g, color = species, shape=island))

ggplotly(p)

library(corrplot)
M<-cor(Clean_DF[3:6])
corrplot(M,method="color",addCoef.col = "white")